Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the topic of knowledge inference, focusing on embedding techniques, recommender systems, and information extraction. It delves into the concept of knowledge graphs, knowledge representation, and link prediction. The instructor discusses the TransE model, link ranking, and the process of performing stochastic gradient descent for knowledge base completion. The lecture also explores label propagation algorithms for inferring attribute values and discusses the challenges of schema matching in integrating heterogeneous data sources.